Merge aef78fdfa8 into a9f85670d0

Closes #10594
Authored by: manavchaudhary1

.github/workflows/build.yml

@@ -411,7 +411,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.11.1-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -460,7 +460,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.11.1-py3-none-any.whl"
 
       - name: Prepare
         run: |

pyproject.toml

@@ -83,7 +83,7 @@ test = [
     "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.10.0",  # Windows temp cleanup fixed in 6.10.0
+    "pyinstaller>=6.11.1",  # Windows temp cleanup fixed in 6.11.1
 ]
 
 [project.urls]

yt_dlp/extractor/_extractors.py

@@ -1156,6 +1156,7 @@ from .mitele import MiTeleIE
 from .mixch import (
     MixchArchiveIE,
     MixchIE,
+    MixchMovieIE,
 )
 from .mixcloud import (
     MixcloudIE,
@@ -1380,15 +1381,15 @@ from .nowness import (
 )
 from .noz import NozIE
 from .npo import (
-    NPOIE,
+    NPO3IE,
+    NTRIE,
     VPROIE,
-    WNLIE,
     AndereTijdenIE,
     HetKlokhuisIE,
-    NPOLiveIE,
-    NPORadioFragmentIE,
     NPORadioIE,
+    NPOStartIE,
     SchoolTVIE,
+    ZappIE,
 )
 from .npr import NprIE
 from .nrk import (
@@ -1939,9 +1940,7 @@ from .spotify import (
 )
 from .spreaker import (
     SpreakerIE,
-    SpreakerPageIE,
     SpreakerShowIE,
-    SpreakerShowPageIE,
 )
 from .springboardplatform import SpringboardPlatformIE
 from .sprout import SproutIE

yt_dlp/extractor/chaturbate.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://www.chaturbate.com/siswet19/',
         'info_dict': {
@@ -29,15 +29,24 @@ class ChaturbateIE(InfoExtractor):
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/siswet19/',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.global/siswet19/',
+        'only_matching': True,
     }]
 
     _ROOM_OFFLINE = 'Room is currently offline'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, tld = self._match_valid_url(url).group('id', 'tld')
 
         webpage = self._download_webpage(
-            f'https://chaturbate.com/{video_id}/', video_id,
+            f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers())
 
         found_m3u8_urls = []

yt_dlp/extractor/cloudflarestream.py

@@ -8,7 +8,7 @@ class CloudflareStreamIE(InfoExtractor):
     _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
     _EMBED_RE = rf'(?:embed\.|{_SUBDOMAIN_RE}){_DOMAIN_RE}/embed/[^/?#]+\.js\?(?:[^#]+&)?video='
     _ID_RE = r'[\da-f]{32}|eyJ[\w-]+\.[\w-]+\.[\w-]+'
-    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}{_DOMAIN_RE}/|{_EMBED_RE})(?P<id>{_ID_RE})'
+    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}(?P<domain>{_DOMAIN_RE})/|{_EMBED_RE})(?P<id>{_ID_RE})'
     _EMBED_REGEX = [
         rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE})(?:(?!\1).)*)\1',
         rf'<iframe[^>]+\bsrc=["\'](?P<url>https?://{_SUBDOMAIN_RE}{_DOMAIN_RE}/[\da-f]{{32}})',
@@ -19,7 +19,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': '31c9291ab41fac05471db4e73aa11717',
             'ext': 'mp4',
             'title': '31c9291ab41fac05471db4e73aa11717',
-            'thumbnail': 'https://videodelivery.net/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
         },
         'params': {
             'skip_download': 'm3u8',
@@ -30,7 +30,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': '0e8e040aec776862e1d632a699edf59e',
             'ext': 'mp4',
             'title': '0e8e040aec776862e1d632a699edf59e',
-            'thumbnail': 'https://videodelivery.net/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
         },
     }, {
         'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -54,7 +54,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': 'eaef9dea5159cf968be84241b5cedfe7',
             'ext': 'mp4',
             'title': 'eaef9dea5159cf968be84241b5cedfe7',
-            'thumbnail': 'https://videodelivery.net/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
         },
         'params': {
             'skip_download': 'm3u8',
@@ -62,8 +62,9 @@ class CloudflareStreamIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, domain = self._match_valid_url(url).group('id', 'domain')
-        domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
+        if domain != 'bytehighway.net':
+            domain = 'cloudflarestream.com'
         base_url = f'https://{domain}/{video_id}/'
         if '.' in video_id:
             video_id = self._parse_json(base64.urlsafe_b64decode(

yt_dlp/extractor/goplay.py

@@ -5,56 +5,63 @@ import hashlib
 import hmac
 import json
 import os
+import re
+import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
+    js_to_json,
+    remove_end,
     traverse_obj,
-    unescapeHTML,
 )
 
 
 class GoPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/]+/[^/]+/|)(?P<display_id>[^/#]+)'
+    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
 
     _NETRC_MACHINE = 'goplay'
 
     _TESTS = [{
-        'url': 'https://www.goplay.be/video/de-container-cup/de-container-cup-s3/de-container-cup-s3-aflevering-2#autoplay',
+        'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
         'info_dict': {
-            'id': '9c4214b8-e55d-4e4b-a446-f015f6c6f811',
+            'id': '2baa4560-87a0-421b-bffc-359914e3c387',
             'ext': 'mp4',
-            'title': 'S3 - Aflevering 2',
+            'title': 'S22 - Aflevering 1',
-            'series': 'De Container Cup',
+            'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
-            'season': 'Season 3',
+            'series': 'De Slimste Mens ter Wereld',
-            'season_number': 3,
+            'episode': 'Episode 1',
-            'episode': 'Episode 2',
+            'season_number': 22,
-            'episode_number': 2,
+            'episode_number': 1,
+            'season': 'Season 22',
         },
+        'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
-        'url': 'https://www.goplay.be/video/a-family-for-thr-holidays-s1-aflevering-1#autoplay',
+        'url': 'https://www.goplay.be/video/1917',
         'info_dict': {
-            'id': '74e3ed07-748c-49e4-85a0-393a93337dbf',
+            'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
             'ext': 'mp4',
-            'title': 'A Family for the Holidays',
+            'title': '1917',
+            'description': r're:Op het hoogtepunt van de Eerste Wereldoorlog krijgen twee jonge .{94}',
         },
+        'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
         'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
         'info_dict': {
-            'id': '03eb8f2f-153e-41cb-9805-0d3a29dab656',
+            'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
             'ext': 'mp4',
             'title': 'S11 - Aflevering 1',
+            'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
             'episode': 'Episode 1',
             'series': 'De Mol',
             'season_number': 11,
             'episode_number': 1,
             'season': 'Season 11',
         },
-        'params': {
+        'params': {'skip_download': True},
-            'skip_download': True,
-        },
         'skip': 'This video is only available for registered users',
     }]
 
@@ -69,27 +76,42 @@ class GoPlayIE(InfoExtractor):
         if not self._id_token:
             raise self.raise_login_required(method='password')
 
-    def _real_extract(self, url):
+    def _find_json(self, s):
-        url, display_id = self._match_valid_url(url).group(0, 'display_id')
+        return self._search_json(
-        webpage = self._download_webpage(url, display_id)
+            r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
-        video_data_json = self._html_search_regex(r'<div\s+data-hero="([^"]+)"', webpage, 'video_data')
-        video_data = self._parse_json(unescapeHTML(video_data_json), display_id).get('data')
 
-        movie = video_data.get('movie')
+    def _real_extract(self, url):
-        if movie:
+        display_id = self._match_id(url)
-            video_id = movie['videoUuid']
+        webpage = self._download_webpage(url, display_id)
-            info_dict = {
+
-                'title': movie.get('title'),
+        nextjs_data = traverse_obj(
-            }
+            re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
-        else:
+            (..., {js_to_json}, {json.loads}, ..., {self._find_json}, ...))
-            episode = traverse_obj(video_data, ('playlists', ..., 'episodes', lambda _, v: v['pageInfo']['url'] == url), get_all=False)
+        meta = traverse_obj(nextjs_data, (
-            video_id = episode['videoUuid']
+            ..., lambda _, v: v['meta']['path'] == urllib.parse.urlparse(url).path, 'meta', any))
-            info_dict = {
+
-                'title': episode.get('episodeTitle'),
+        video_id = meta['uuid']
-                'series': traverse_obj(episode, ('program', 'title')),
+        info_dict = traverse_obj(meta, {
-                'season_number': episode.get('seasonNumber'),
+            'title': ('title', {str}),
-                'episode_number': episode.get('episodeNumber'),
+            'description': ('description', {str.strip}),
-            }
+        })
+
+        if traverse_obj(meta, ('program', 'subtype')) != 'movie':
+            for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
+                episode_data = traverse_obj(
+                    season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
+                if not episode_data:
+                    continue
+
+                episode_title = traverse_obj(
+                    episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
+                info_dict.update({
+                    'title': episode_title or info_dict.get('title'),
+                    'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
+                    'season_number': traverse_obj(season_data, ('season', {int_or_none})),
+                    'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
+                })
+                break
 
         api = self._download_json(
             f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',

yt_dlp/extractor/mixch.py

@@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
 
 class MixchIE(InfoExtractor):
     IE_NAME = 'mixch'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/u/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://mixch.tv/u/16943797/live',
@@ -74,7 +74,7 @@ class MixchIE(InfoExtractor):
 
 class MixchArchiveIE(InfoExtractor):
     IE_NAME = 'mixch:archive'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/archive/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://mixch.tv/archive/421',
@@ -116,3 +116,56 @@ class MixchArchiveIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
             'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
         }
+
+
+class MixchMovieIE(InfoExtractor):
+    IE_NAME = 'mixch:movie'
+    _VALID_URL = r'https?://mixch\.tv/m/(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'https://mixch.tv/m/Ve8KNkJ5',
+        'info_dict': {
+            'id': 'Ve8KNkJ5',
+            'title': '夏☀️\nムービーへのポイントは本イベントに加算されないので配信にてお願い致します🙇🏻\u200d♀️\n#TGCCAMPUS #ミス東大 #ミス東大2024 ',
+            'ext': 'mp4',
+            'uploader': 'ミス東大No.5 松藤百香🍑💫',
+            'uploader_id': '12299174',
+            'channel_follower_count': int,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'timestamp': 1724070828,
+            'uploader_url': 'https://mixch.tv/u/12299174',
+            'live_status': 'not_live',
+            'upload_date': '20240819',
+        },
+    }, {
+        'url': 'https://mixch.tv/m/61DzpIKE',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            f'https://mixch.tv/api-web/movies/{video_id}', video_id)
+        return {
+            'id': video_id,
+            'formats': [{
+                'format_id': 'mp4',
+                'url': data['movie']['file'],
+                'ext': 'mp4',
+            }],
+            **traverse_obj(data, {
+                'title': ('movie', 'title', {str}),
+                'thumbnail': ('movie', 'thumbnailURL', {url_or_none}),
+                'uploader': ('ownerInfo', 'name', {str}),
+                'uploader_id': ('ownerInfo', 'id', {int}, {str_or_none}),
+                'channel_follower_count': ('ownerInfo', 'fan', {int_or_none}),
+                'view_count': ('ownerInfo', 'view', {int_or_none}),
+                'like_count': ('movie', 'favCount', {int_or_none}),
+                'comment_count': ('movie', 'commentCount', {int_or_none}),
+                'timestamp': ('movie', 'published', {int_or_none}),
+                'uploader_url': ('ownerInfo', 'id', {lambda x: x and f'https://mixch.tv/u/{x}'}, filter),
+            }),
+            'live_status': 'not_live',
+        }

yt_dlp/extractor/npo.py

@@ -1,606 +1,438 @@
-import random
+import json
 import re
-import urllib.parse
+
+from yt_dlp.utils._utils import ExtractorError
+from yt_dlp.utils.traversal import traverse_obj
 
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     int_or_none,
-    merge_dicts,
     orderedSet,
-    str_or_none,
-    try_call,
-    unified_timestamp,
-    url_or_none,
-    urlencode_postdata,
 )
 
 
-class NPOIE(InfoExtractor):
+class NPOBaseIE(InfoExtractor):
-    IE_NAME = 'npo'
+    def _extract_product_id_information(self, product_id):
-    IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
+        token = self._download_json(
-    _VALID_URL = r'''(?x)
+            f'https://npo.nl/start/api/domain/player-token?productId={product_id}', product_id,
-                    (?:
+            'Downloading token')['token']
-                        npo:|
+        return self._extract_info_from_token(product_id, token)
-                        https?://
-                            (?:www\.)?
-                            (?:
-                                npo\.nl/(?:[^/]+/)*|
-                                (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
-                                omroepwnl\.nl/video/fragment/[^/]+__|
-                                (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
-                            )
-                        )
-                        (?P<id>[^/?#]+)
-                '''
 
-    _TESTS = [{
+    def _extract_info_from_token(self, video_id, token):
-        'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
+        data = {
-        'md5': '4b3f9c429157ec4775f2c9cb7b911016',
+            'id': video_id,
-        'info_dict': {
+        }
-            'id': 'VPWON_1220719',
-            'ext': 'm4v',
-            'title': 'Nieuwsuur',
-            'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
-            'upload_date': '20140622',
-        },
-        'skip': 'Video was removed',
-    }, {
-        'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
-        'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
-        'info_dict': {
-            'id': 'VARA_101191800',
-            'ext': 'm4v',
-            'title': 'De Mega Mike & Mega Thomas show: The best of.',
-            'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
-            'upload_date': '20090227',
-            'duration': 2400,
-        },
-        'skip': 'Video was removed',
-    }, {
-        'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
-        'md5': '1b279c0547f6b270e014c576415268c5',
-        'info_dict': {
-            'id': 'VPWON_1169289',
-            'ext': 'mp4',
-            'title': 'Zwart geld: de toekomst komt uit Afrika',
-            'description': 'md5:dffaf3d628a9c36f78ca48d834246261',
-            'upload_date': '20130225',
-            'duration': 3000,
-            'creator': 'NED2',
-            'series': 'Tegenlicht',
-            'timestamp': 1361822340,
-            'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg',
-            'episode': 'Zwart geld: de toekomst komt uit Afrika',
-            'episode_number': 18,
-        },
-    }, {
-        'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
-        'info_dict': {
-            'id': 'WO_VPRO_043706',
-            'ext': 'mp4',
-            'title': 'De nieuwe mens - Deel 1',
-            'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
-            'duration': 4680,
-            'episode': 'De nieuwe mens - Deel 1',
-            'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg',
-            'timestamp': 1279716057,
-            'series': 'De nieuwe mens - Deel 1',
-            'upload_date': '20100721',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        # non asf in streams
-        'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
-        'info_dict': {
-            'id': 'WO_NOS_762771',
-            'ext': 'mp4',
-            'title': 'Hoe gaat Europa verder na Parijs?',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Video was removed',
-    }, {
-        'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
-        'info_dict': {
-            'id': 'VPWON_1233944',
-            'ext': 'mp4',
-            'title': 'Aap, poot, pies',
-            'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6',
-            'upload_date': '20150508',
-            'duration': 599,
-            'episode': 'Aap, poot, pies',
-            'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg',
-            'timestamp': 1431064200,
-            'series': 'Aap, poot, pies',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
-        'info_dict': {
-            'id': 'POW_00996502',
-            'ext': 'm4v',
-            'title': '''"Dit is wel een 'landslide'..."''',
-            'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
-            'upload_date': '20150508',
-            'duration': 462,
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Video was removed',
-    }, {
-        # audio
-        'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
-        'info_dict': {
-            'id': 'RBX_FUNX_6683215',
-            'ext': 'mp3',
-            'title': 'Jouw Stad Rotterdam',
-            'description': 'md5:db251505244f097717ec59fabc372d9f',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Video was removed',
-    }, {
-        'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
-        'only_matching': True,
-    }, {
-        # live stream
-        'url': 'npo:LI_NL1_4188102',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
-        'only_matching': True,
-    }, {
-        'url': 'https://npo.nl/KN_1698996',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105',
-        'info_dict': {
-            'id': 'VPWON_1341105',
-            'ext': 'mp4',
-            'duration': 2658,
-            'series': 'The Genius',
-            'description': 'md5:db02f1456939ca63f7c408f858044e94',
-            'title': 'The Genius',
-            'timestamp': 1669062000,
-            'creator': 'NED3',
-            'episode': 'The Genius',
-            'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg',
-            'episode_number': 8,
-            'upload_date': '20221121',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }]
-
-    @classmethod
-    def suitable(cls, url):
-        return (False if any(ie.suitable(url)
-                for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
-                else super().suitable(url))
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']:
-            player = self._download_json(
-                f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id,
-                'Downloading player JSON', query={
-                    'parameters[elementId]': f'npo{random.randint(0, 999)}',
-                    'parameters[sterReferralUrl]': url,
-                    'parameters[autoplay]': 0,
-                })
-        else:
-            self._request_webpage(
-                'https://www.npostart.nl/api/token', video_id,
-                'Downloading token', headers={
-                    'Referer': url,
-                    'X-Requested-With': 'XMLHttpRequest',
-                })
-            player = self._download_json(
-                f'https://www.npostart.nl/player/{video_id}', video_id,
-                'Downloading player JSON', data=urlencode_postdata({
-                    'autoplay': 0,
-                    'share': 1,
-                    'pageUrl': url,
-                    'hasAdConsent': 0,
-                }), headers={
-                    'x-xsrf-token': try_call(lambda: urllib.parse.unquote(
-                        self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)),
-                })
-
-        player_token = player['token']
-
-        drm = False
-        format_urls = set()
         formats = []
-        for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
+        thumbnails = []
-            streams = self._download_json(
+        subtitles = {}
-                f'https://start-player.npo.nl/video/{video_id}/streams',
+        for profile_name in ('dash', 'hls', 'smooth'):
-                video_id, f'Downloading {profile} profile JSON', fatal=False,
+            profile = self._download_json(
-                query={
+                'https://prod.npoplayer.nl/stream-link',
-                    'profile': profile,
+                video_id,
-                    'quality': 'npoplus',
+                f'Downloading profile {profile_name} JSON',
-                    'tokenId': player_token,
+                data=json.dumps({'profileName': profile_name}).encode(),
-                    'streamType': 'broadcast',
+                headers={'Authorization': token},
-                }, data=b'')  # endpoint requires POST
+                fatal=False,
-            if not streams:
+            )
-                continue
+            metadata = profile.get('metadata')
-            stream = streams.get('stream')
+            if metadata is not None:
-            if not isinstance(stream, dict):
+                duration = metadata.get('duration')
-                continue
+                thumbnail = metadata.get('poster')
-            stream_url = url_or_none(stream.get('src'))
+                data['title'] = metadata.get('title')
-            if not stream_url or stream_url in format_urls:
+                data['description'] = metadata.get('description')
-                continue
+                data['channel_id'] = metadata.get('channel')
-            format_urls.add(stream_url)
+                data['uploader_id'] = metadata.get('channel')
-            if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
+                data['genres'] = metadata.get('genres')
-                drm = True
+                if duration:
-                continue
+                    data['duration'] = duration / 1000
-            stream_type = stream.get('type')
+                if thumbnail and not any(thumb['url'] == thumbnail for thumb in thumbnails):
+                    thumbnails.append({
+                        'url': thumbnail,
+                    })
+            raw_subtitles = traverse_obj(profile, ('assets', 'subtitles'))
+            stream_url = traverse_obj(profile, ('stream', 'streamURL'))
             stream_ext = determine_ext(stream_url)
-            if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
+            if stream_ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
-                    stream_url, video_id, mpd_id='dash', fatal=False))
+                    stream_url, video_id=video_id, mpd_id='dash', fatal=False))
-            elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
+            elif stream_ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    stream_url, video_id, ext='mp4',
+                    stream_url, video_id=video_id, ext='mp4',
                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
             elif re.search(r'\.isml?/Manifest', stream_url):
                 formats.extend(self._extract_ism_formats(
-                    stream_url, video_id, ism_id='mss', fatal=False))
+                    stream_url, video_id=video_id, ism_id='mss', fatal=False))
             else:
                 formats.append({
                     'url': stream_url,
                 })
-
+            if (raw_subtitles):
-        if not formats:
+                for subtitle in raw_subtitles:
-            if not self.get_param('allow_unplayable_formats') and drm:
+                    tag = subtitle.get('iso')
-                self.report_drm(video_id)
+                    if tag not in subtitles:
-
+                        subtitles[tag] = []
-        info = {
+                    if not any(sub['url'] == subtitle['location'] for sub in subtitles[tag]):
-            'id': video_id,
+                        subtitles[tag].append({
-            'title': video_id,
+                            'url': subtitle.get('location'),
-            'formats': formats,
+                            'name': subtitle.get('name'),
-        }
-
-        embed_url = url_or_none(player.get('embedUrl'))
-        if embed_url:
-            webpage = self._download_webpage(
-                embed_url, video_id, 'Downloading embed page', fatal=False)
-            if webpage:
-                video = self._parse_json(
-                    self._search_regex(
-                        r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
-                        default='{}'), video_id)
-                if video:
-                    title = video.get('episodeTitle')
-                    subtitles = {}
-                    subtitles_list = video.get('subtitles')
-                    if isinstance(subtitles_list, list):
-                        for cc in subtitles_list:
-                            cc_url = url_or_none(cc.get('src'))
-                            if not cc_url:
-                                continue
-                            lang = str_or_none(cc.get('language')) or 'nl'
-                            subtitles.setdefault(lang, []).append({
-                                'url': cc_url,
                         })
-                    return merge_dicts({
+        data['formats'] = formats
-                        'title': title,
+        data['subtitles'] = subtitles
-                        'description': video.get('description'),
+        data['thumbnails'] = thumbnails
-                        'thumbnail': url_or_none(
+        return data
-                            video.get('still_image_url') or video.get('orig_image_url')),
-                        'duration': int_or_none(video.get('duration')),
-                        'timestamp': unified_timestamp(video.get('broadcastDate')),
-                        'creator': video.get('channel'),
-                        'series': video.get('title'),
-                        'episode': title,
-                        'episode_number': int_or_none(video.get('episodeNumber')),
-                        'subtitles': subtitles,
-                    }, info)
-
-        return info
 
 
-class NPOLiveIE(InfoExtractor):
+class NPOStartIE(NPOBaseIE):
-    IE_NAME = 'npo.nl:live'
+    IE_NAME = 'npo.nl:start'
-    _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
 
     _TESTS = [{
-        'url': 'http://www.npo.nl/live/npo-1',
+        'url': 'https://npo.nl/start/serie/vpro-tegenlicht/seizoen-11/zwart-geld-de-toekomst-komt-uit-afrika/afspelen',
+        'md5': '8c30593a81ac80d65b531eaf2a92ac02',
         'info_dict': {
-            'id': 'LI_NL1_4188102',
+            'id': 'VPWON_1169289',
-            'display_id': 'npo-1',
             'ext': 'mp4',
-            'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': 'Zwart geld: de toekomst komt uit Afrika',
-            'is_live': True,
+            'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+            'duration': 3000,
+            'uploader_id': 'NED2',
+            'series': 'VPRO Tegenlicht',
+            'timestamp': 1361822340,
+            'thumbnail': 'https://assets-start.npo.nl/resources/2023/06/30/d9879593-1944-4249-990c-1561dac14d8e.jpg',
+            'episode': 'Zwart geld: de toekomst komt uit Afrika',
+            'episode_number': 18,
+            'channel_id': 'NED2',
+            'genres': [],
+            'release_date': '20130225',
+            'release_timestamp': 1361822340,
+            'season': 'Season 11',
+            'season_id': 'df5e2334-e07a-4301-b3d3-8e224d8c1f07',
+            'season_number': 11,
+            'series_id': '6727dcdf-4bd2-477c-bf96-1ead69fad6c9',
+            'upload_date': '20130225',
         },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.npo.nl/live',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.npostart.nl/live/npo-1',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url) or 'npo-1'
+        slug = self._match_id(url)
+        metadata = self._download_json(f'https://npo.nl/start/api/domain/program-detail?slug={slug}', video_id=slug, note='Downloading program details JSON')
+        video_id = metadata['productId']
+        data = self._extract_product_id_information(video_id)
+        thumbnails = []
+        for image in metadata.get('images'):
+            thumbnails.append({
+                'id': image.get('guid'),
+                'url': image.get('url'),
+            })
+            break
 
-        webpage = self._download_webpage(url, display_id)
+        data['title'] = metadata.get('title') or data.get('title')
-
+        data['episode'] = metadata.get('title') or data.get('title')
-        live_id = self._search_regex(
+        data['episode_number'] = int_or_none(metadata.get('programKey'))
-            [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
+        data['duration'] = int_or_none(metadata.get('durationInSeconds'), default=data.get('duration'))
-
+        data['description'] = traverse_obj(metadata, ('synopsis', 'long')) or traverse_obj(metadata, ('synopsis', 'short')) or traverse_obj(metadata, ('synopsis', 'brief')) or data.get('description')
-        return {
+        data['thumbnails'] = thumbnails
-            '_type': 'url_transparent',
+        data['genres'] = metadata.get('genres') or data.get('genres')
-            'url': f'npo:{live_id}',
+        data['series'] = traverse_obj(metadata, ('series', 'title'))
-            'ie_key': NPOIE.ie_key(),
+        data['series_id'] = traverse_obj(metadata, ('series', 'guid'))
-            'id': live_id,
+        data['season_number'] = int_or_none(traverse_obj(metadata, ('season', 'seasonKey')))
-            'display_id': display_id,
+        data['season_id'] = traverse_obj(metadata, ('season', 'guid'))
-        }
+        data['release_timestamp'] = int_or_none(metadata.get('firstBroadcastDate'))
+        data['timestamp'] = int_or_none(metadata.get('publishedDateTime'))
+        return data
 
 
-class NPORadioIE(InfoExtractor):
+class NPORadioIE(NPOBaseIE):
     IE_NAME = 'npo.nl:radio'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?nporadio(?P<n>\d)\.nl(?:/[^/]+)*/(?P<id>[^/]+)?'
 
-    _TEST = {
+    _TESTS = [{
-        'url': 'http://www.npo.nl/radio/radio-1',
+        'url': 'https://www.nporadio1.nl/',
         'info_dict': {
-            'id': 'radio-1',
+            'id': 'live',
-            'ext': 'mp3',
+            'ext': 'mp4',
-            'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': r're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'live_status': 'is_live',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'description': 'Live programmering',
             'is_live': True,
         },
         'params': {
             'skip_download': True,
         },
-    }
+    },
-
+        {
-    @classmethod
+        'url': 'https://www.nporadio1.nl/nieuws/binnenland/15bcad75-22c5-4226-a3fe-d54a76175da3/utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
-    def suitable(cls, url):
+        'md5': '8ad04123febc07716f45e324d7fb792d',
-        return False if NPORadioFragmentIE.suitable(url) else super().suitable(url)
+        'info_dict': {
-
+            'id': 'utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
-    @staticmethod
+            'ext': 'mp4',
-    def _html_get_attribute_regex(attribute):
+            'duration': 262,
-        return rf'{attribute}\s*=\s*\'([^\']+)\''
+            'channel_id': 'RAD1',
+            'description': 'md5:7d36b72407e757e6c748a6cdf27c7628',
+            'title': 'Utrecht zet rolmodellen in voor bewustzijn mentale gezondheid ',
+            'genres': ['Informatief'],
+            'uploader_id': 'RAD1',
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2217026',
+        },
+    },
+        {
+        'url': 'https://www.nporadio2.nl/fragmenten/janwillemstartop/9d35b8fb-a07b-41f9-9cc5-a9c89dd60dbb/2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
+        'md5': '432b0e106082ffaa0e31c4549db09b0c',
+        'info_dict': {
+            'id': '2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
+            'ext': 'mp4',
+            'genres': ['Muziek'],
+            'title': 'Nancy zet zich in voor daklozen: "Voor mij was het op het randje" ',
+            'duration': 235,
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2216783',
+            'description': 'md5:26925e8bd2c715b160cc864efa731583',
+            'uploader_id': 'RAD2',
+            'channel_id': 'RAD2',
+        },
+    },
+        {
+        'url': 'https://www.nporadio2.nl/uitzendingen/dit-is-tannaz/9bc1ab7e-77f6-4444-986b-1cd7c25ff4bf/2024-10-11-dit-is-tannaz',
+        'md5': 'a1212f4d2fe361aafcced5bcd3cf939b',
+        'info_dict': {
+            'id': '2024-10-11-dit-is-tannaz',
+            'ext': 'mp3',
+            'uploader_id': 'RAD2',
+            'genres': ['Muziek'],
+            'title': 'Dit is Tannaz',
+            'channel_id': 'RAD2',
+            'description': 'md5:3f2b5dad3e965ae7915a5f9a5a2decc5',
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2190854',
+            'duration': 7200.026,
+        },
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        parsed = self._match_valid_url(url)
+        video_id = parsed.group('id') or 'live'
 
-        webpage = self._download_webpage(url, video_id)
+        if video_id == 'live':
-
+            radio_number = parsed.group('n')
-        title = self._html_search_regex(
+            token_url = self._download_json(f'https://www.nporadio{radio_number}.nl/api/player/npo-radio-{radio_number}', video_id)['tokenUrl']
-            self._html_get_attribute_regex('data-channel'), webpage, 'title')
+        else:
-
+            props = self._search_nextjs_data(self._download_webpage(url, video_id), video_id)['props']['pageProps']
-        stream = self._parse_json(
+            token_url = traverse_obj(props, ('article', 'content', 0, 'value', 'player', 'tokenUrl')) or traverse_obj(props, ('fragmentDetail', 'bodyContent', 0, 'payload', 'player', 'tokenUrl')) or traverse_obj(props, ('radioBroadcast', 'showAssets', 0, 'player', 'tokenUrl'))
-            self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
+        if token_url is None:
-            video_id)
+            raise ExtractorError('Token url not found')
-
+        data = self._extract_info_from_token(video_id, self._download_json(token_url, video_id, 'Downloading token JSON')['playerToken'])
-        codec = stream.get('codec')
+        data['is_live'] = video_id == 'live'
-
+        return data
-        return {
-            'id': video_id,
-            'url': stream['url'],
-            'title': title,
-            'acodec': codec,
-            'ext': codec,
-            'is_live': True,
-        }
 
 
-class NPORadioFragmentIE(InfoExtractor):
+class NPO3IE(NPOBaseIE):
-    IE_NAME = 'npo.nl:radio:fragment'
+    IE_NAME = 'npo.nl:npo3'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/npo3/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
 
     _TEST = {
-        'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
+        'url': 'https://npo.nl/npo3/vlees-smakelijk/11-10-2024/WO_KN_20222563',
-        'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
+        'md5': 'e0cd5b96c712edea2e7f0700d348bc98',
         'info_dict': {
-            'id': '174356',
+            'id': 'WO_KN_20222563',
-            'ext': 'mp3',
+            'ext': 'mp4',
-            'title': 'Jubileumconcert Willeke Alberti',
+            'description': 'md5:31f5ffff8c70af1635cbb93a8205e0c4',
+            'duration': 1021.994,
+            'title': 'Vlees smakelijk',
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2215940',
+            'genres': ['Human Interest', 'Reality TV'],
         },
     }
 
     def _real_extract(self, url):
-        audio_id = self._match_id(url)
+        return self._extract_product_id_information(self._match_id(url))
-
-        webpage = self._download_webpage(url, audio_id)
-
-        title = self._html_search_regex(
-            rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"',
-            webpage, 'title')
-
-        audio_url = self._search_regex(
-            r"data-streams='([^']+)'", webpage, 'audio url')
-
-        return {
-            'id': audio_id,
-            'url': audio_url,
-            'title': title,
-        }
 
 
-class NPODataMidEmbedIE(InfoExtractor):  # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
+class SchoolTVIE(NPOBaseIE):
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(
-            r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
-        return {
-            '_type': 'url_transparent',
-            'ie_key': 'NPO',
-            'url': f'npo:{video_id}',
-            'display_id': display_id,
-        }
-
-
-class SchoolTVIE(NPODataMidEmbedIE):
     IE_NAME = 'schooltv'
-    _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P<id>[^/?#&]+)'
 
     _TEST = {
-        'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
+        'url': 'https://schooltv.nl/video-item/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
         'info_dict': {
             'id': 'WO_NTR_429477',
-            'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
-            'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
             'ext': 'mp4',
-            'description': 'md5:abfa0ff690adb73fd0297fd033aaa631',
+            'duration': 51.0,
-        },
+            'genres': ['Jeugd'],
-        'params': {
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/242560',
-            # Skip because of m3u8 download
+            'title': 'Ademhaling',
-            'skip_download': True,
+            'description': 'md5:db41d874d9ebe597686dda69e892ba49',
         },
     }
 
+    def _real_extract(self, url):
+        video_id = self._search_regex(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url))), 'video id')
+        return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
 
-class HetKlokhuisIE(NPODataMidEmbedIE):
+
+class HetKlokhuisIE(NPOBaseIE):
     IE_NAME = 'hetklokhuis'
-    _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TEST = {
-        'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
+        'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens',
+        'md5': '679d610017689ecc798b316b8daa34e7',
         'info_dict': {
-            'id': 'VPWON_1260528',
+            'id': 'VPWON_1225126',
-            'display_id': 'Zwaartekrachtsgolven',
+            'ext': 'mp4',
-            'ext': 'm4v',
+            'duration': 852.27,
-            'title': 'Het Klokhuis: Zwaartekrachtsgolven',
+            'channel_id': 'NED3',
-            'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
+            'description': 'md5:17681c9644521344a0573e04c78912d7',
-            'upload_date': '20170223',
+            'title': 'Aliens',
-        },
+            'genres': ['Jeugd', 'Informatief'],
-        'params': {
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/624824',
-            'skip_download': True,
+            'uploader_id': 'NED3',
+            'series': 'Zoek Het Uit!',
         },
     }
 
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, self._match_id(url))
+        series, title = self._og_search_title(webpage).split(' - ')
+        video_id = self._html_search_regex(r'data-mid="([a-zA-Z0-9_]+)"', webpage, 'video id')
+        data = self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
+        data['series'] = series
+        data['title'] = title
+        return data
+
+
+class ZappIE(NPOBaseIE):
+    IE_NAME = 'zapp.nl'
+    _VALID_URL = r'https?://(?:www\.)?zapp\.nl/programmas/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
+
+    _TEST = {
+        'url': 'https://www.zapp.nl/programmas/zappsport/gemist/POMS_AT_811523',
+        'md5': 'faf6811abea03ba8a52298c97bd0146b',
+        'info_dict': {
+            'id': 'POMS_AT_811523',
+            'ext': 'mp4',
+            'genres': [],
+            'uploader_id': 'NED3',
+            'description': 'Kindersportprogramma waarin alle takken van sport voorbijkomen.',
+            'channel_id': 'NED3',
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/586056',
+            'duration': 900.0,
+            'title': 'Running Team 2015 - aflevering 1',
+        },
+    }
+
+    def _real_extract(self, url):
+        return self._extract_product_id_information(self._match_id(url))
+
+
+class NPOPlaylistBaseIE(NPOBaseIE):
+    def _mid_result(self, mid, title, url):
+        token = self._download_token(mid, url)
+        data = self._extract_info_from_token(mid, token)
+        # The API returns the same title for every video so overwrite it with the video title
+        data['title'] = title
+        return data
 
-class NPOPlaylistBaseIE(NPOIE):  # XXX: Do not subclass from concrete IE
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = [
-            self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id)
-            for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
-        ]
-
         playlist_title = self._html_search_regex(
             self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
             default=None) or self._og_search_title(webpage)
 
+        entries = [
+            self._mid_result(video_id, playlist_title, url)
+            for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
+        ]
+
         return self.playlist_result(entries, playlist_id, playlist_title)
 
 
 class VPROIE(NPOPlaylistBaseIE):
     IE_NAME = 'vpro'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/.]+)'
-    _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
+    _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)')
-                          r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 
     _TESTS = [
         {
-            'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
+            'url': 'https://www.vpro.nl/programmas/3doc/2015/sergio-herman.html',
-            'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
-            'info_dict': {
-                'id': 'VPWON_1169289',
-                'ext': 'm4v',
-                'title': 'De toekomst komt uit Afrika',
-                'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
-                'upload_date': '20130225',
-            },
-            'skip': 'Video gone',
-        },
-        {
-            'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
             'info_dict': {
                 'id': 'sergio-herman',
-                'title': 'sergio herman: fucking perfect',
+                'title': 'Sergio Herman: Fucking Perfect',
-            },
-            'playlist_count': 2,
-        },
-        {
-            # playlist with youtube embed
-            'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
-            'info_dict': {
-                'id': 'education-education',
-                'title': 'education education',
             },
             'playlist_count': 2,
         },
         {
             'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
+            'md5': '87a4cc5a62da942ca9270e4da1d2b8b5',
             'info_dict': {
-                'id': 'de-tegenprestatie',
+                'id': 'VPWON_1223413',
+                'ext': 'mp4',
                 'title': 'De Tegenprestatie',
+                'duration': 2992.45,
+                'genres': ['Documentaire'],
+                'channel_id': 'NED2',
+                'description': 'Er wordt van burgers steeds meer eigen verantwoordelijkheid en zelfredzaamheid gevraagd.',
+                'uploader_id': 'NED2',
+                'thumbnail': 'https://images.poms.omroep.nl/image/s1080/663342',
             },
-            'playlist_count': 2,
         }, {
-            'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
+            'url': 'https://www.2doc.nl/documentaires/2018/07/het-verdriet-van-nederland.html',
+            'md5': '9ae67f6bdcb16a62f99e01198674fe10',
             'info_dict': {
                 'id': 'VARA_101375237',
-                'ext': 'm4v',
+                'ext': 'mp4',
-                'title': 'MH17: Het verdriet van Nederland',
+                'uploader_id': 'NED1',
-                'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
+                'channel_id': 'NED1',
-                'upload_date': '20150716',
+                'thumbnail': 'https://images.poms.omroep.nl/image/s1080/1608566',
-            },
+                'duration': 4259.63,
-            'params': {
+                'genres': ['Documentaire'],
-                # Skip because of m3u8 download
+                'title': 'Het verdriet van Nederland',
-                'skip_download': True,
+                'description': 'md5:d19b745af196f6cb98daf50ac7cb01fc',
             },
         },
     ]
 
+    def _download_token(self, mid, url):
+        return self._download_json('https://rs.vpro.nl/v3/api/npoplayer/token', mid, 'Downloading token JSON', data=json.dumps({'mid': mid}).encode(), headers={
+            'Content-Type': 'application/json',
+            'Referer': url,
+        })['token']
 
-class WNLIE(NPOPlaylistBaseIE):
+
-    IE_NAME = 'wnl'
+class NTRIE(NPOPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
+    IE_NAME = 'ntr'
-    _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
+    _VALID_URL = r'https?://(?:www\.)?ntr\.nl/(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
+    _PLAYLIST_TITLE_RE = r'<h2[^>]*>\s*(.+)\s*</h2>'
+    _PLAYLIST_ENTRY_RE = r'<div[^>]+class=["\']npo_wrapper["\'][^>]+data-mid=["\'](.+?)["\']'
 
     _TESTS = [{
-        'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
+        'url': 'https://ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944',
+        'md5': '5b7b45c15750c9a74f8b70ea69f0b55a',
         'info_dict': {
-            'id': 'vandaag-de-dag-6-mei',
+            'id': 'VPWON_1233944',
-            'title': 'Vandaag de Dag 6 mei',
+            'ext': 'mp4',
+            'duration': 599.98,
+            'channel_id': 'NED3',
+            'genres': ['Jeugd', 'Serie'],
+            'description': 'Appie en Aisia mogen beurtelings mee met hun vader Luc, die in de dierentuin werkt.',
+            'uploader_id': 'NED3',
+            'title': 'Aap, poot, pies',
+            'thumbnail': 'https://images.poms.omroep.nl/image/s1080/608116',
         },
-        'playlist_count': 4,
     }]
 
+    def _download_token(self, mid, url):
+        return self._download_json(f'https://ntr.nl/ajax/player/embed/{mid}', mid, 'Downloading token JSON')['jwt']
 
-class AndereTijdenIE(NPOPlaylistBaseIE):
+
+class AndereTijdenIE(NTRIE):
     IE_NAME = 'anderetijden'
     _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
-    _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
+    _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container\s+episode-page["\'][^>]+data-mid=["\'](.+?)["\']'
 
     _TESTS = [{
         'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',

yt_dlp/extractor/rutube.py

@@ -2,15 +2,18 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    UnsupportedError,
     bool_or_none,
     determine_ext,
     int_or_none,
+    js_to_json,
     parse_qs,
-    traverse_obj,
+    str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class RutubeBaseIE(InfoExtractor):
@@ -19,7 +22,7 @@ class RutubeBaseIE(InfoExtractor):
             query = {}
         query['format'] = 'json'
         return self._download_json(
-            f'http://rutube.ru/api/video/{video_id}/',
+            f'https://rutube.ru/api/video/{video_id}/',
             video_id, 'Downloading video JSON',
             'Unable to download video JSON', query=query)
 
@@ -61,18 +64,21 @@ class RutubeBaseIE(InfoExtractor):
             query = {}
         query['format'] = 'json'
         return self._download_json(
-            f'http://rutube.ru/api/play/options/{video_id}/',
+            f'https://rutube.ru/api/play/options/{video_id}/',
             video_id, 'Downloading options JSON',
             'Unable to download options JSON',
             headers=self.geo_verification_headers(), query=query)
 
-    def _extract_formats(self, options, video_id):
+    def _extract_formats_and_subtitles(self, options, video_id):
         formats = []
+        subtitles = {}
         for format_id, format_url in options['video_balancer'].items():
             ext = determine_ext(format_url)
             if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
             elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
                     format_url, video_id, f4m_id=format_id, fatal=False))
@@ -82,11 +88,19 @@ class RutubeBaseIE(InfoExtractor):
                     'format_id': format_id,
                 })
         for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
-            formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
-        return formats
+                hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
+            subtitles.setdefault(caption.get('code') or 'ru', []).append({
+                'url': caption['file'],
+                'name': caption.get('langTitle'),
+            })
+        return formats, subtitles
 
-    def _download_and_extract_formats(self, video_id, query=None):
+    def _download_and_extract_formats_and_subtitles(self, video_id, query=None):
-        return self._extract_formats(
+        return self._extract_formats_and_subtitles(
             self._download_api_options(video_id, query=query), video_id)
 
 
@@ -97,8 +111,8 @@ class RutubeIE(RutubeBaseIE):
     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
 
     _TESTS = [{
-        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        'md5': 'e33ac625efca66aba86cbec9851f2692',
+        'md5': '3d73fdfe5bb81b9aef139e22ef3de26a',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
             'ext': 'mp4',
@@ -111,26 +125,25 @@ class RutubeIE(RutubeBaseIE):
             'upload_date': '20131016',
             'age_limit': 0,
             'view_count': int,
-            'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
             'categories': ['Новости и СМИ'],
             'chapters': [],
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
-        'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
+        'url': 'https://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
-        'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
+        'url': 'https://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
-        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
+        'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
         'only_matching': True,
     }, {
         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
         'only_matching': True,
     }, {
         'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
-        'md5': 'd106225f15d625538fe22971158e896f',
+        'md5': '4fce7b4fcc7b1bcaa3f45eb1e1ad0dd7',
         'info_dict': {
             'id': '884fb55f07a97ab673c7d654553e0f48',
             'ext': 'mp4',
@@ -143,11 +156,10 @@ class RutubeIE(RutubeBaseIE):
             'upload_date': '20221210',
             'age_limit': 0,
             'view_count': int,
-            'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
             'categories': ['Видеоигры'],
             'chapters': [],
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
         'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
         'info_dict': {
@@ -156,17 +168,16 @@ class RutubeIE(RutubeBaseIE):
             'chapters': 'count:4',
             'categories': ['Бизнес и предпринимательство'],
             'description': 'md5:252feac1305257d8c1bab215cedde75d',
-            'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
+            'thumbnail': 'https://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
             'duration': 782,
             'age_limit': 0,
             'uploader_id': '23491359',
             'timestamp': 1677153329,
             'view_count': int,
             'upload_date': '20230223',
-            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
+            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании #1',
             'uploader': 'Стас Быков',
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
         'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
         'info_dict': {
@@ -174,7 +185,7 @@ class RutubeIE(RutubeBaseIE):
             'ext': 'mp4',
             'categories': ['Телепередачи'],
             'description': '',
-            'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
             'live_status': 'is_live',
             'age_limit': 0,
             'uploader_id': '23460655',
@@ -184,6 +195,24 @@ class RutubeIE(RutubeBaseIE):
             'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
             'uploader': 'Первый канал',
         },
+    }, {
+        'url': 'https://rutube.ru/play/embed/03a9cb54bac3376af4c5cb0f18444e01/',
+        'info_dict': {
+            'id': '03a9cb54bac3376af4c5cb0f18444e01',
+            'ext': 'mp4',
+            'age_limit': 0,
+            'description': '',
+            'title': 'Церемония начала торгов акциями ПАО «ЕвроТранс»',
+            'chapters': [],
+            'upload_date': '20240829',
+            'duration': 293,
+            'uploader': 'MOEX - Московская биржа',
+            'timestamp': 1724946628,
+            'thumbnail': 'https://pic.rutubelist.ru/video/2e/24/2e241fddb459baf0fa54acfca44874f4.jpg',
+            'view_count': int,
+            'uploader_id': '38420507',
+            'categories': ['Интервью'],
+        },
     }, {
         'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
         'only_matching': True,
@@ -192,40 +221,46 @@ class RutubeIE(RutubeBaseIE):
         'only_matching': True,
     }]
 
-    @classmethod
-    def suitable(cls, url):
-        return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         query = parse_qs(url)
         info = self._download_and_extract_info(video_id, query)
-        info['formats'] = self._download_and_extract_formats(video_id, query)
+        formats, subtitles = self._download_and_extract_formats_and_subtitles(video_id, query)
-        return info
+        return {
+            **info,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
 
 
 class RutubeEmbedIE(RutubeBaseIE):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
-    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)(?:[?#/]|$)'
 
     _TESTS = [{
-        'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
+        'url': 'https://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
             'ext': 'mp4',
             'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
-            'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
             'uploader': 'subziro89 ILya',
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
+            'age_limit': 0,
+            'duration': 1395,
+            'chapters': [],
+            'description': 'md5:a5acea57bbc3ccdc3cacd1f11a014b5b',
+            'view_count': int,
+            'thumbnail': 'https://pic.rutubelist.ru/video/d3/03/d3031f4670a6e6170d88fb3607948418.jpg',
+            'categories': ['Сериалы'],
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'http://rutube.ru/play/embed/8083783',
+        'url': 'https://rutube.ru/play/embed/8083783',
         'only_matching': True,
     }, {
         # private video
@@ -240,11 +275,12 @@ class RutubeEmbedIE(RutubeBaseIE):
         query = parse_qs(url)
         options = self._download_api_options(embed_id, query)
         video_id = options['effective_video']
-        formats = self._extract_formats(options, video_id)
+        formats, subtitles = self._extract_formats_and_subtitles(options, video_id)
         info = self._download_and_extract_info(video_id, query)
         info.update({
             'extractor_key': 'Rutube',
             'formats': formats,
+            'subtitles': subtitles,
         })
         return info
 
@@ -295,14 +331,14 @@ class RutubeTagsIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube tags'
     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://rutube.ru/tags/video/1800/',
+        'url': 'https://rutube.ru/tags/video/1800/',
         'info_dict': {
             'id': '1800',
         },
         'playlist_mincount': 68,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
 
 class RutubeMovieIE(RutubePlaylistBaseIE):
@@ -310,8 +346,8 @@ class RutubeMovieIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 
-    _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
+    _MOVIE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/?format=json'
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 
     def _real_extract(self, url):
         movie_id = self._match_id(url)
@@ -327,62 +363,82 @@ class RutubePersonIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://rutube.ru/video/person/313878/',
+        'url': 'https://rutube.ru/video/person/313878/',
         'info_dict': {
             'id': '313878',
         },
-        'playlist_mincount': 37,
+        'playlist_mincount': 36,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json'
 
 
 class RutubePlaylistIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:playlist'
     IE_DESC = 'Rutube playlists'
-    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
+    _VALID_URL = r'https?://rutube\.ru/plst/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
+        'url': 'https://rutube.ru/plst/308547/',
         'info_dict': {
-            'id': '3097',
+            'id': '308547',
         },
-        'playlist_count': 27,
+        'playlist_mincount': 22,
-    }, {
-        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
-        'only_matching': True,
     }]
-
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/playlist/custom/%s/videos?page=%s&format=json'
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
-
-    @classmethod
-    def suitable(cls, url):
-        from ..utils import int_or_none, parse_qs
-
-        if not super().suitable(url):
-            return False
-        params = parse_qs(url)
-        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
-
-    def _next_page_url(self, page_num, playlist_id, item_kind):
-        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
-
-    def _real_extract(self, url):
-        qs = parse_qs(url)
-        playlist_kind = qs['pl_type'][0]
-        playlist_id = qs['pl_id'][0]
-        return self._extract_playlist(playlist_id, item_kind=playlist_kind)
 
 
 class RutubeChannelIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channel'
-    _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
+    _VALID_URL = r'https?://rutube\.ru/(?:channel/(?P<id>\d+)|u/(?P<slug>\w+))(?:/(?P<section>videos|shorts|playlists))?'
     _TESTS = [{
         'url': 'https://rutube.ru/channel/639184/videos/',
         'info_dict': {
-            'id': '639184',
+            'id': '639184_videos',
         },
-        'playlist_mincount': 133,
+        'playlist_mincount': 129,
+    }, {
+        'url': 'https://rutube.ru/channel/25902603/shorts/',
+        'info_dict': {
+            'id': '25902603_shorts',
+        },
+        'playlist_mincount': 277,
+    }, {
+        'url': 'https://rutube.ru/channel/25902603/',
+        'info_dict': {
+            'id': '25902603',
+        },
+        'playlist_mincount': 406,
+    }, {
+        'url': 'https://rutube.ru/u/rutube/videos/',
+        'info_dict': {
+            'id': '23704195_videos',
+        },
+        'playlist_mincount': 113,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json&origin__type=%s'
+
+    def _next_page_url(self, page_num, playlist_id, section):
+        origin_type = {
+            'videos': 'rtb,rst,ifrm,rspa',
+            'shorts': 'rshorts',
+            None: '',
+        }.get(section)
+        return self._PAGE_TEMPLATE % (playlist_id, page_num, origin_type)
+
+    def _real_extract(self, url):
+        playlist_id, slug, section = self._match_valid_url(url).group('id', 'slug', 'section')
+        if section == 'playlists':
+            raise UnsupportedError(url)
+        if slug:
+            webpage = self._download_webpage(url, slug)
+            redux_state = self._search_json(
+                r'window\.reduxState\s*=', webpage, 'redux state', slug, transform_source=js_to_json)
+            playlist_id = traverse_obj(redux_state, (
+                'api', 'queries', lambda k, _: k.startswith('channelIdBySlug'),
+                'data', 'channel_id', {int}, {str_or_none}, any))
+        playlist = self._extract_playlist(playlist_id, section=section)
+        if section:
+            playlist['id'] = f'{playlist_id}_{section}'
+        return playlist

yt_dlp/extractor/spreaker.py

@@ -2,13 +2,16 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    filter_dict,
     float_or_none,
     int_or_none,
+    parse_qs,
     str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 def _extract_episode(data, episode_id=None):
@@ -58,15 +61,10 @@ def _extract_episode(data, episode_id=None):
 
 
 class SpreakerIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
+    _VALID_URL = [
-                    https?://
+        r'https?://api\.spreaker\.com/(?:(?:download/)?episode|v2/episodes)/(?P<id>\d+)',
-                        api\.spreaker\.com/
+        r'https?://(?:www\.)?spreaker\.com/episode/[^#?/]*?(?P<id>\d+)/?(?:[?#]|$)',
-                        (?:
+    ]
-                            (?:download/)?episode|
-                            v2/episodes
-                        )/
-                        (?P<id>\d+)
-                    '''
     _TESTS = [{
         'url': 'https://api.spreaker.com/episode/12534508',
         'info_dict': {
@@ -83,7 +81,9 @@ class SpreakerIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
             'comment_count': int,
-            'series': 'Success With Music (SWM)',
+            'series': 'Success With Music | SWM',
+            'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/777ce4f96b71b0e1b7c09a5e625210e3.jpg',
+            'creators': ['SWM'],
         },
     }, {
         'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
@@ -91,52 +91,75 @@ class SpreakerIE(InfoExtractor):
     }, {
         'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
         'only_matching': True,
+    }, {
+        'note': 'episode',
+        'url': 'https://www.spreaker.com/episode/grunge-music-origins-the-raw-sound-that-defined-a-generation--60269615',
+        'info_dict': {
+            'id': '60269615',
+            'display_id': 'grunge-music-origins-the-raw-sound-that-',
+            'ext': 'mp3',
+            'title': 'Grunge Music Origins - The Raw Sound that Defined a Generation',
+            'description': str,
+            'timestamp': 1717468905,
+            'upload_date': '20240604',
+            'uploader': 'Katie Brown 2',
+            'uploader_id': '17733249',
+            'duration': 818.83,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'series': '90s Grunge',
+            'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/bb0d4178f7cf57cc8786dedbd9c5d969.jpg',
+            'creators': ['Katie Brown 2'],
+        },
+    }, {
+        'url': 'https://www.spreaker.com/episode/60269615',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         episode_id = self._match_id(url)
         data = self._download_json(
-            f'https://api.spreaker.com/v2/episodes/{episode_id}',
+            f'https://api.spreaker.com/v2/episodes/{episode_id}', episode_id,
-            episode_id)['response']['episode']
+            query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode']
         return _extract_episode(data, episode_id)
 
 
-class SpreakerPageIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        episode_id = self._search_regex(
-            (r'data-episode_id=["\'](?P<id>\d+)',
-             r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
-        return self.url_result(
-            f'https://api.spreaker.com/episode/{episode_id}',
-            ie=SpreakerIE.ie_key(), video_id=episode_id)
-
-
 class SpreakerShowIE(InfoExtractor):
-    _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
+    _VALID_URL = [
+        r'https?://api\.spreaker\.com/show/(?P<id>\d+)',
+        r'https?://(?:www\.)?spreaker\.com/podcast/[\w-]+--(?P<id>[\d]+)',
+        r'https?://(?:www\.)?spreaker\.com/show/(?P<id>\d+)/episodes/feed',
+    ]
     _TESTS = [{
         'url': 'https://api.spreaker.com/show/4652058',
         'info_dict': {
             'id': '4652058',
         },
         'playlist_mincount': 118,
+    }, {
+        'url': 'https://www.spreaker.com/podcast/health-wealth--5918323',
+        'info_dict': {
+            'id': '5918323',
+        },
+        'playlist_mincount': 60,
+    }, {
+        'url': 'https://www.spreaker.com/show/5887186/episodes/feed',
+        'info_dict': {
+            'id': '5887186',
+        },
+        'playlist_mincount': 290,
     }]
 
-    def _entries(self, show_id):
+    def _entries(self, show_id, key=None):
         for page_num in itertools.count(1):
             episodes = self._download_json(
                 f'https://api.spreaker.com/show/{show_id}/episodes',
-                show_id, note=f'Downloading JSON page {page_num}', query={
+                show_id, note=f'Downloading JSON page {page_num}', query=filter_dict({
                     'page': page_num,
                     'max_per_page': 100,
-                })
+                    'key': key,
+                }))
             pager = try_get(episodes, lambda x: x['response']['pager'], dict)
             if not pager:
                 break
@@ -152,21 +175,5 @@ class SpreakerShowIE(InfoExtractor):
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+        key = traverse_obj(parse_qs(url), ('key', 0))
-
+        return self.playlist_result(self._entries(show_id, key), playlist_id=show_id)
-
-class SpreakerShowPageIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/show/success-with-music',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        show_id = self._search_regex(
-            r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
-        return self.url_result(
-            f'https://api.spreaker.com/show/{show_id}',
-            ie=SpreakerShowIE.ie_key(), video_id=show_id)